This article investigates whether it is possible to segment continuous speech on word and phrasal level by examination of suprasegmental parameters, in case of bound stress languages like Hungarian and Finnish. The final aim is to increase the robustness of speech recognition on language modelling level by the detection of word and phrase boundaries and so we can significantly decrease the sear...

BACKGROUND While previous studies have shown that children affected by dyslexia exhibit a deficit in categorical perception of segmental features in alphabetic languages, it remains unclear whether the categorical perception deficit generalizes to nonalphabetic languages at the suprasegmental level. In this study, we investigated the occurrence of categorical perception deficit in Mandarin lexi...

This is an attempt to show structured heterogeneity of English stress variants by applying a Labovian quantitative study to suprasegmental variation. Compared with the relatively frequent occurrence of segmental variation such as [Hŋ] ~[Hm\ hm ,hmf+ the low frequency of suprasegmental variation makes it difficult to observe differences of pronunciation in different styles. A detailed analysis o...

In this paper I shall present a treatment of lexical and grammatical tone and vowel length in Hausa, as implemented in an emerging bidirectional HPSG of the language based on the Lingo Grammar Matrix (Bender et al., 2002). I shall argue in particular that a systematic treatment of suprasegmental phonology is indispensible in an implemented grammar of the language, both for theoretical and pract...

The task of automatically segmenting an acoustic signal into categories (such as speech, speech over background music, or music) is an important step in the transcription process. We are attempting to improve the accuracy of such segmentation systems by incorporating suprasegmental and other temporal information into the frame-based classifiers typically used for this purpose. Two specific appr...

In the last decade there has been an increasing tendency to incorporate language engineering strategies into speech technology. This technique combines linguistic and mathematical information in different applications: machine translation, natural language processing, speech synthesis and automatic speech recognition (ASR). In the field of speech synthesis, this hybrid approach (linguistic and ...

As a preliminary step towards conducting a teacher survey on pronunciation teaching in order to design a phonetics course for current and prospective English teachers in Japan, this paper analyses six governmentapproved English textbooks used in junior high schools. The purposes are to examine the types of pronunciation activities in the textbooks and to discuss the knowledge of phonetics requi...

This paper investigates the classification of different emotional states using speech features from different feature groups. We use both suprasegmental feature groups like pitch, energy, and duration and segmental feature groups like voice quality, zero crossing rate, and articulation. We want to exploit the selection of the most relevant features from these different feature groups to get a b...

It has been long held that segmental and prosodic aspects of speech belong to very different domains. Segments refer to vowels and consonants which constitute the phonemes that make up the words of speech, and they are what most writing systems record. As such they are viewed as the core components of speech. Prosodic components, also known as suprasegmentals, refer to properties like stress, t...